© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107389
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥ¨
    -0.31
    æĦıè§ģ
    -0.27
    åħĪæĺ¯
    -0.26
     sworn
    -0.25
     divisions
    -0.25
     spaces
    -0.24
     Held
    -0.24
    spaces
    -0.24
    ç»ĨåĪĨ
    -0.24
    ä¸įå¿į
    -0.23
    POSITIVE LOGITS
    ator
    0.27
    ç»Ŀç¼ĺ
    0.27
    ah
    0.26
    vit
    0.25
    flammatory
    0.24
     vibration
    0.23
    .djangoproject
    0.23
    çĺ¦
    0.23
    ite
    0.23
    æĢ»èĢĮè¨Ģä¹ĭ
    0.23
    Activations Density 1.270%

    No Known Activations

    This feature has no known activations.